import pandas as pd
import seaborn as sns
import plotly.express as px

import matplotlib.pyplot as plt
from matplotlib.pyplot import figure
import matplotlib.dates as mdates

import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"

Matplotlib

For this excercise, we have written the following code to load the stock dataset built into plotly express.

stocks = px.data.stocks()
stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

Question 1:

Select a stock and create a suitable plot for it. Make sure the plot is readable with relevant information, such as date, values.

# YOUR CODE HERE
plot = stocks.plot(x = 'date', y = 'AAPL')
plot.set_ylabel('stock value')
plot.set_title('AAPL')
plt.rcParams["figure.figsize"] = (15,10)


plt.show()

Question 2:

You've already plot data from one stock. It is possible to plot multiples of them to support comparison.
To highlight different lines, customise line styles, markers, colors and include a legend to the plot.

# YOUR CODE HERE
plot = stocks.plot(x = 'date', y = ['AAPL','GOOG','AMZN','FB','NFLX','MSFT'])
plot.set_ylabel('stock value')
plot.set_title('Stocks')
plt.rcParams["figure.figsize"] = (15,10)

Seaborn

First, load the tips dataset

tips = sns.load_dataset('tips')
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

Question 3:

Let's explore this dataset. Pose a question and create a plot that support drawing answers for your question.

Some possible questions:

• Are there differences between male and female when it comes to giving tips?
• What attribute correlate the most with tip?

# YOUR CODE HERE
print('On which day(s) employees receive the most tip and is this correlated to the type of dinner on that day?')
plot = sns.FacetGrid(tips, col='day', hue='time')
plot.map(sns.scatterplot, 'total_bill', 'tip')
plot.add_legend()
plt.show()

On which day(s) employees receive the most tip and is this correlated to the type of dinner on that day?

Plotly Express

Question 4:

Redo the above exercises (challenges 2 & 3) with plotly express. Create diagrams which you can interact with.

The stocks dataset

Hints:

• Turn stocks dataframe into a structure that can be picked up easily with plotly express

# YOUR CODE HERE
df = px.data.stocks() 
fig = px.line(df, x="date", y=['AAPL','GOOG','AMZN','FB','NFLX','MSFT'])
fig.show()

The tips dataset

# YOUR CODE HERE
df = px.data.tips() 
print('On which day(s) employees receive the most tip and is this correlated to the type of dinner on that day?')
fig = px.scatter(df, x="total_bill", y="tip", color="time", facet_col="day")
fig.show()

On which day(s) employees receive the most tip and is this correlated to the type of dinner on that day?

Question 5:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

# YOUR CODE HERE
year_2007 = df['year'] == 2007
df[year_2007]

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
11	Afghanistan	Asia	2007	43.828	31889923	974.580338	AFG	4
23	Albania	Europe	2007	76.423	3600523	5937.029526	ALB	8
35	Algeria	Africa	2007	72.301	33333216	6223.367465	DZA	12
47	Angola	Africa	2007	42.731	12420476	4797.231267	AGO	24
59	Argentina	Americas	2007	75.320	40301927	12779.379640	ARG	32
...	...	...	...	...	...	...	...	...
1655	Vietnam	Asia	2007	74.249	85262356	2441.576404	VNM	704
1667	West Bank and Gaza	Asia	2007	73.422	4018332	3025.349798	PSE	275
1679	Yemen, Rep.	Asia	2007	62.698	22211743	2280.769906	YEM	887
1691	Zambia	Africa	2007	42.384	11746035	1271.211593	ZMB	894
1703	Zimbabwe	Africa	2007	43.487	12311143	469.709298	ZWE	716

142 rows × 8 columns

df_data_2007 = df.query('year == 2007')
df_data_2007_new = df_data_2007.groupby('continent').sum()
fig = px.bar(df_data_2007_new, x = 'pop', orientation = 'h', color = df_data_2007_new.index, text_auto = '.4s')
fig.update_yaxes(categoryorder = 'total ascending')

fig.show()